Find the most active users in Amplitude, check your Google Calendar for open slots, and create personalised Gmail drafts inviting them to a research interview. Never sends — always saves as drafts for your review. Use when planning a user research sprint.
70
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The SKILL.md explicitly instructs the agent to fetch user records and activity from Amplitude (Step 1) and to use that user-generated, third-party data to personalise Gmail drafts, so untrusted Amplitude content could indirectly inject instructions that influence the agent's drafting behavior.
51838c2
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.